8:00 AM PST | Event Kickoff – Agenda Review Host: Rajeev Nalawadi (Intel) ONNX Progress Update Speakers: ONNX Steering Committee Prasanth, Alex, Mayank, Wenming, Rajeev |
8:15 AM PST | Community Presentations – Agenda Review ONNX SC Member ONNX Runtime Web: Running Your Machine Learning Model in Browser Speaker: Emma Ning (Microsoft) ONNX as a Standard Format for Institution with Legacy Speaker: Haixuan Xavier Tao ( Banque France) ONNX and the AI on IBM Z Client Journey Speaker(s): Elpida Tzortzatos & Andrew M. Sica (IBM) Intel® Neural Compressor: A Scalable Quantization Tool for ONNX Models Speaker: Mengni Wang (Intel) Ascend CANN and ONNX : Inference Interoperability for Better Performance Speaker: Zhipeng Huang (Huawei) Intel® OneAPI software stack: ONNX Support for xPU Hardware Speaker: Kiefer Kuah (Intel) ONNX: Boosting PaddlePaddle Deployment in Industry Speaker: Ti Zhou (Baidu) Auditing Considerations for ONNX Models and Benchmarking with QuSandbox Speaker: Sri Krishnamurthy (QuantUniversity) TVM: Dynamic Shapes, Control Flow, and Quantization with a Compiler Speaker: Jason Knight (OctoML) & Andrew Luo (OctoML) Place of ONNX in OpenVINO Ecosystem Speaker: Sergey Lyalin (Intel) Triton & ONNX Runtime Speaker: Ashwini Khade (Microsoft) |
10:10 AM PST | SIGs and WGs Updates – Agenda Review ONNX SC Member Architecture/Infrastructure SIG Update Co-Chairs: Ashwini Khade (Microsoft) Operators SIG Update Co-Chairs: Michal Karzynski (Intel), Ganesan Ramalingam (Microsoft) Converters SIG Update Co-Chairs: Chin Huang (IBM), Guenther Schmuelling (Microsoft) Model Zoo / Tutorials SIG Update Co-Chairs: Wenbing Li (Microsoft) & Mark Hamilton (Microsoft) Pre-processing WG Co-chairs: Joaquin Anton (Nvidia) Q&A and Meetup Conclusion ONNX SC Member |